hf-cli
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to us
npx skills add waybarrios/opencode-power-pack --skill hf-cli --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill directs the agent to use the Hugging Face Hub CLI (hf) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. It triggers when users mention 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or related phrases, or express intent to perform Hugging Face ecosystem or AI/ML tasks. It also covers cloud storage needs like training checkpoints, data pipelines, or agent traces and notes that the hf command replaces the deprecated huggingface-cli.
How it works
- Provide installation guidance: use the command
curl -LsSf https://hf.co/cli/install.sh | bash -s. - Instruct to view available functions with
hf --help, noting auth commands are underhf auth(e.g.,hf auth whoami). - List of commands includes
hf cp,hf download,hf env,hf sync,hf update,hf upload,hf upload-large-folder(deprecated),hf version. - Authentication subcommands under
hf authincludelist,login,logout,switch,token,whoami. - Bucket-related commands under
hf bucketsincludecp,create,delete,info,list,move,remove,sync. - Cache management under
hf cachewithlist,prune,rm,verify. - Collections, datasets, discussions, endpoints, extensions, jobs have corresponding subcommands, such as
hf collections list,hf datasets list,hf discussions list,hf endpoints list,hf extensions list,hf jobs list. - Each command entry lists its syntax and options, e.g.,
hf download REPO_IDwith flags like--type,--revision,--include,--exclude, etc.
When to use it
Use when the user mentions Hugging Face Hub operations, authentication needs, cache management, bucket management, running or scheduling jobs on HF infrastructure, managing HF repos, discussions/pull requests, browsing models/datasets/spaces, reading papers, managing collections, querying datasets, configuring spaces, webhooks, or HF Inference Endpoints. Also use for cloud storage like training checkpoints or agent traces. Use even if not explicitly asked for a CLI command.
What it can touch
- Commands and subcommands of the hf CLI as listed:
hf cp,hf download,hf env,hf sync,hf update,hf upload,hf version,hf auth,hf buckets,hf cache,hf collections,hf datasets,hf discussions,hf endpoints,hf extensions,hf jobs. - No external files or tools are named beyond those in the command list; quotes and exact spellings must be preserved in usage.
Caveats
- Replaces the deprecated
huggingface-cli. - Install command provided:
curl -LsSf https://hf.co/cli/install.sh | bash -s. - Mentions deprecated
hf upload-large-folderas [Deprecated]. - License is Apache-2.0 (modified; see UPSTREAMS.json).
Install: `curl -LsSf https://hf.co/cli/install.sh | bash -s`. The Hugging Face Hub CLI tool `hf` is available. IMPORTANT: The `hf` command replaces the deprecated `huggingface-cli` command. Use `hf --help` to view available functions. Note that auth commands are now all under `hf auth` e.g. `hf auth whoami`. Generated with `huggingface_hub v1.23.0`. Run `hf skills add --force` to regenerate. ## Commands - `hf cp SRC` — Copy files between local paths, repositories, and buckets. `[--format [auto|human|agent|json|quiet]]` - `hf download REPO_ID` — Download files from the Hub. `[--type [model|dataset|space] --revision TEXT --include TEXT --exclude TEXT --cache-dir TEXT --local-dir TEXT --force-download --dry-run --max-workers INTEGER --format [auto|human|agent|json|quiet]]` - `hf env` — Print information about the environment. `[--format [auto|human|agent|json|quiet]]` - `hf sync` — Sync files between local directory and a bucket. `[--delete --ignore-times --ignore-sizes --plan TEXT --apply TEXT --dry-run --include TEXT --exclude TEXT --filter-from TEXT --existing --ignore-existing --verbose --format [auto|human|agent|json|quiet]]` - `hf update` — Update the `hf` CLI to the latest vers
- Commands
- hf auth — Manage authentication (login, logout, etc.).
- hf buckets — Commands to interact with buckets.
- hf cache — Manage local cache directory.
- hf collections — Interact with collections on the Hub.
- hf datasets — Interact with datasets on the Hub.
- hf discussions — Manage discussions and pull requests on the Hub.
- hf endpoints — Manage Hugging Face Inference Endpoints.
- hf extensions — Manage hf CLI extensions.
- hf jobs — Run and manage Jobs on the Hub.
- hf models — Interact with models on the Hub.
- hf papers — Interact with papers on the Hub.
- hf repos — Manage repos on the Hub.
- hf sandbox — Run and manage sandboxes on Hugging Face Jobs.
What does the hf-cli skill do?
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to us
How do I install it?
Run `npx skills add waybarrios/opencode-power-pack --skill hf-cli --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From waybarrios/opencode-power-pack, a repository with 443 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.